抄録
Road detection is an important research subject in autonomous driving. Both accuracy and efficiency are very important for road detection used in autonomous driving systems. However, these two properties are usually contradictory under certain calculation resources. In this paper, we make a good compromise between accuracy and efficiency by proposing a dual-stage detecting strategy, which consists of a fast Hough transform based road detection method and a reliable vanishing point based method. A dynamic region of interest (ROI) is proposed as a connector of the two stages. Experiments prove that our method can achieve good performance on both accuracy and efficiency.
| 本文言語 | English |
|---|---|
| ホスト出版物のタイトル | Proceedings of 2017 9th International Conference on Computer and Automation Engineering, ICCAE 2017 |
| 出版社 | Association for Computing Machinery |
| ページ | 155-162 |
| ページ数 | 8 |
| 巻 | Part F127852 |
| ISBN（電子版） | 9781450348096 |
| DOI | |
| 出版ステータス | Published - 2017 2 18 |
| イベント | 9th International Conference on Computer and Automation Engineering, ICCAE 2017 - Sydney, Australia 継続期間: 2017 2 18 → 2017 2 21 |
Other
| Other | 9th International Conference on Computer and Automation Engineering, ICCAE 2017 |
|---|---|
| Country | Australia |
| City | Sydney |
| Period | 17/2/18 → 17/2/21 |
ASJC Scopus subject areas
- Human-Computer Interaction
- Computer Networks and Communications
- Computer Vision and Pattern Recognition
- Software